| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-nova - 2025-10-02 | |||
| 14:05:29 | opendevreview | Takashi Kajinami proposed openstack/os-resource-classes master: Drop basepython https://review.opendev.org/c/openstack/os-resource-classes/+/962806 | |
| 14:05:45 | opendevreview | Takashi Kajinami proposed openstack/os-traits master: Drop basepython https://review.opendev.org/c/openstack/os-traits/+/962805 | |
| 14:10:45 | tkajinam | anyone care to merge these trivial changes ? https://review.opendev.org/c/openstack/os-resource-classes/+/947488 https://review.opendev.org/c/openstack/os-resource-classes/+/932878 | |
| 14:17:08 | sean-k-mooney | done | |
| 14:17:22 | sean-k-mooney | well for the last 2 | |
| 14:17:27 | gibi | done | |
| 14:17:34 | gibi | ahh | |
| 14:17:38 | tkajinam | thanks both ! | |
| 14:17:44 | gibi | :) | |
| 14:18:14 | sean-k-mooney | the basepython thing we can do | |
| 14:18:22 | sean-k-mooney | but it also will nto break anything if we never do it | |
| 14:18:44 | sean-k-mooney | so ill look at it eventually but i need to go rebase things | |
| 14:18:55 | sean-k-mooney | so ill try to remember to loop back | |
| 14:24:21 | opendevreview | Merged openstack/os-resource-classes master: Drop unnecessary 'x' bit from doc config file https://review.opendev.org/c/openstack/os-resource-classes/+/932878 | |
| 14:31:56 | opendevreview | Merged openstack/os-resource-classes master: Replace UPPER_CONSTRAINTS_FILE https://review.opendev.org/c/openstack/os-resource-classes/+/947488 | |
| 15:50:25 | opendevreview | Merged openstack/os-traits master: Drop basepython https://review.opendev.org/c/openstack/os-traits/+/962805 | |
| 15:55:17 | opendevreview | Merged openstack/nova master: Run nova-conductor in native threading mode https://review.opendev.org/c/openstack/nova/+/958575 | |
| 16:18:33 | lajoskatona | sean-k-mooney: after some desperate reading in n-client, neutron and nova I think the exotic exceptions like IpAddressGenerationFailureClient & ExternalIpAddressExhaustedClient and all similar ones are not really used anymore | |
| 16:18:51 | lajoskatona | sean-k-mooney: https://review.opendev.org/c/openstack/nova/+/962604/1/nova/network/neutron.py#b3099 | |
| 16:20:14 | lajoskatona | as I see the method allocate_floating_ip is only called from nova/api/openstack/compute/floating_ips.py which is if I understand well is the deprecated FIP API in Nova which calls to Neutron (https://docs.openstack.org/api-ref/compute/#floating-ips-os-floating-ips-deprecated ) | |
| 16:20:53 | lajoskatona | sean-k-mooney: am I thinking the right way or I am totally lost in how these API exceptions work? | |
| 16:22:57 | lajoskatona | I checked on the Neutron side and for IpAddressGenerationFailureClient for example that catches the Neutron ipam http "exception" https://opendev.org/openstack/neutron/src/branch/master/neutron/ipam/exceptions.py#L62 | |
| 16:25:22 | lajoskatona | I am not sure how that is done to tell the truth, but anyway the Neutron ipam IpAddressGenerationFailure 's base is Conflict so I can check the inside of the SDK ConflictException to check for msg "No more IP addresses available for subnet..." | |
| 16:27:14 | sean-k-mooney | lajoskatona: ack reading back | |
| 16:28:05 | lajoskatona | so summary (I think) 1.) part of these exception consumer methods are for deprecated Nova APIs (/os-floating-ips) 2.) it seems that as Neutron packs the msg of the http rsp with definite msg (like "No more IP addresses available for subnet....") I can catch these messages and raise different nova exceptions back based on the message | |
| 16:28:41 | lajoskatona | sean-k-mooney: thanks, it is a summary for myself also to not forget it for tomorrow :-) | |
| 16:28:57 | sean-k-mooney | lajoskatona: i belive you are correct that is is realted to the porxy apis | |
| 16:29:10 | sean-k-mooney | nova does not to my knowlage allcoate floating ips internally | |
| 16:29:22 | sean-k-mooney | so i cant think of any other reasonable usage of those methods | |
| 16:30:01 | lajoskatona | sean-k-mooney: ack, so the possibility that I break something important is lower :-) | |
| 16:30:15 | lajoskatona | that is always good news .... | |
| 16:32:21 | sean-k-mooney | yep | |
| 16:33:06 | sean-k-mooney | the other thing to consier is while the error code is part of the api contract the exact details of the error message isnt nessisarly part of it | |
| 16:33:40 | sean-k-mooney | so if we anted to make these proxy apis bevhve a little more like neturon wew could but if we can do the convertion without a visible impact that is stil probly better | |
| 17:06:28 | noonedeadpunk | hey folks! I've spotted that there's a spec regarding iothreads for virto-blk lying here: https://review.opendev.org/c/openstack/nova-specs/+/951636 | |
| 17:06:43 | noonedeadpunk | which should be placed to 2026.1 I guess | |
| 17:06:51 | noonedeadpunk | But I have a different, but related question | |
| 17:07:33 | noonedeadpunk | I've spotted there's also an scsi blueprint without spec: https://blueprints.launchpad.net/nova/+spec/libvirt-add-support-for-virtio-scsi-multiqueue | |
| 17:09:19 | noonedeadpunk | it seems that these 2 should not be conflicting with each other and I assume both can be implemented? | |
| 17:11:14 | noonedeadpunk | as if I'm not mistaken, that Windows virtio-blk driver is always a single queue, so the way to get any disk performance on windows would be to have scsi and multiqueue there | |
| 17:16:15 | noonedeadpunk | jsut trying to validate if I'm sane and can proceed to working on spec :) | |
| 17:16:27 | noonedeadpunk | (or it could be specless one) | |
| 17:17:39 | dansmith | noonedeadpunk: we have at least three things that are all related, so probably best to have a PTG discussion on it | |
| 17:18:02 | dansmith | domain iothreads, device iothread pinning, and any of these queue things are probably related enough to combine into a single conversation | |
| 17:18:05 | noonedeadpunk | also ports multique I guess? | |
| 17:18:16 | noonedeadpunk | yeah | |
| 17:18:20 | noonedeadpunk | fair enough | |
| 19:47:20 | opendevreview | melanie witt proposed openstack/nova master: DNM vtpm tempest https://review.opendev.org/c/openstack/nova/+/957477 | |
| 20:10:26 | sean-k-mooney | noonedeadpunk: https://review.opendev.org/c/openstack/nova-specs/+/953940 i sthe related one that we created to try and scope down the propsoal to make some progres in 2025.2 but that also got hit by spec freeze | |
| 20:11:31 | sean-k-mooney | noonedeadpunk: im hoping that Masahito will pick up the prosal again this cycle if they have time | |
| 20:12:59 | sean-k-mooney | this was the other thing they were interested in https://review.opendev.org/c/openstack/nova-specs/+/938823 | |
| 20:14:04 | sean-k-mooney | so there multiple iothreds, mapping disk queues to iothread and filterign service by netwrok id | |
| 20:14:14 | sean-k-mooney | i dont know which is there priority | |
| 20:15:56 | sean-k-mooney | noonedeadpunk: im just siging off for today but i assuem you want to progress the live migration concurncy feture as well in 2026.1 | |
| 20:16:12 | sean-k-mooney | i know there was some code up for that but i lost track for where that review was | |
| 20:16:44 | sean-k-mooney | noonedeadpunk: this was your spec for that https://review.opendev.org/c/openstack/nova-specs/+/955783 | |
| 20:17:01 | sean-k-mooney | but i also belive there was a specless blueprint approved indepently? | |
| 20:18:19 | sean-k-mooney | this was your bluepint https://blueprints.launchpad.net/nova/+spec/libvirt-parallel-migrate but https://blueprints.launchpad.net/nova/+spec/libvirt-migrate-parallel | |
| 20:18:29 | sean-k-mooney | was appoved then deferd | |
| 20:20:03 | sean-k-mooney | noonedeadpunk: so we currently have two competing propsoals for this one form you and another form Fabian Wiesel | |
| 20:22:58 | sean-k-mooney | noonedeadpunk: given they have revierd and +1 your versiohn i assume yours is the one that we inteded ot proceed with but we shoudl abandon one fo them and if decied if its goign to be specless or requrie a spec | |
| 20:24:41 | sean-k-mooney | Uggla: fyi ^ do you have any prefernce on which of the two blueprint we use and if we want to proceed specless or not | |
| 20:34:16 | melwitt | sean-k-mooney: do you happen to know if this needs to be changed to something else, perhaps devstack@q-ovn-metadata-agent ? now that q-agt is not used? https://github.com/openstack/nova/blob/master/roles/run-evacuate-hook/tasks/main.yaml#L24 | |
| 20:35:37 | melwitt | I'm working on vtpm tempest tests and noticed the error "controller | Unit devstack@q-agt.service could not be found." in the zuul stream | |
| 23:10:42 | opendevreview | melanie witt proposed openstack/nova master: DNM vtpm tempest https://review.opendev.org/c/openstack/nova/+/957477 | |
| 23:10:43 | opendevreview | melanie witt proposed openstack/nova master: TPM: add documentation and reno for live migration https://review.opendev.org/c/openstack/nova/+/962889 | |
| 23:21:33 | opendevreview | melanie witt proposed openstack/nova master: TPM: add documentation and reno for live migration https://review.opendev.org/c/openstack/nova/+/962889 | |
| 23:21:33 | opendevreview | melanie witt proposed openstack/nova master: DNM vtpm tempest https://review.opendev.org/c/openstack/nova/+/957477 | |
| #openstack-nova - 2025-10-03 | |||
| 07:02:57 | noonedeadpunk | sean-k-mooney: Uggla fwiw, I also have an implementation for parallel live migrations as well: https://review.opendev.org/c/openstack/nova/+/955784 | |
| 07:03:59 | noonedeadpunk | and yeah, I missed the specless one when was working on it :( | |
| 07:05:25 | bauzas | sounds to me a good PTG discussion anyway :) | |
| 07:05:51 | bauzas | it looks like we have a momentum, it would be sad to not having anything for Gazpacho :) | |
| 07:06:20 | noonedeadpunk | and regarding iothreads - I think I have yet another thing to add. or well. there is a specless blueprint already, and I have minimal implementation | |
| 07:06:34 | noonedeadpunk | yeah, totally sounds like a good topic for the PTG | |
| 07:06:44 | Uggla | noonedeadpunk That's a bit sad, to have competing proposal. Anyway yes I agree let's discuss that at PTG. | |
| 07:07:28 | noonedeadpunk | Uggla: they are *exactly* the same | |
| 07:07:36 | noonedeadpunk | so nothing sad I guess | |
| 07:08:54 | bauzas | oh yeah, that just means this should be a good and important effort for this cycle :) | |
| 07:08:57 | noonedeadpunk | I even come up with exactly same config name | |
| 07:09:11 | noonedeadpunk | without seeing yours | |
| 07:09:18 | bauzas | do you read minds ? don't reply, I'm afraid of the answer | |
| 07:09:18 | Uggla | sad because we have to choose one and for one of you, it is a "waste" of time. | |
| 07:09:59 | bauzas | were the competing blueprints both accepted ? | |
| 07:10:12 | noonedeadpunk | neither was so far | |
| 07:10:18 | noonedeadpunk | and one blueprint is specless | |
| 07:10:21 | noonedeadpunk | another has a spec | |
| 07:10:34 | bauzas | if not, that's understandable that two different people can start working on a same feature, while nothing is communicated | |
| 07:10:36 | noonedeadpunk | and given implementation is the same, I don;'t think much time was wasted | |
| 07:10:58 | noonedeadpunk | btw | |
| 07:11:12 | noonedeadpunk | author of https://blueprints.launchpad.net/nova/+spec/libvirt-migrate-parallel voted positively on my implementation :) | |
| 07:11:28 | bauzas | that's cool | |
| 07:11:29 | noonedeadpunk | So they are at least aware of this | |
| 07:14:11 | noonedeadpunk | but regarding iothreads, I think I have one more thing to add on top of https://review.opendev.org/c/openstack/nova-specs/+/938823 and https://review.opendev.org/c/openstack/nova-specs/+/951636 | |
| 07:15:25 | noonedeadpunk | or well. let's discuss on PTG :D | |
| 07:15:28 | bauzas | not sure I understand the relationship between io threads and network IDs, but that's probably related to some network IO concern. Anyway, let's wrap that for the PTG | |
| 07:16:12 | noonedeadpunk | if you get into umbrella of "improving guest performance and enable threading capabilities exposed by libvirt" - they are | |
| 07:16:16 | noonedeadpunk | but yeah | |
| 07:16:44 | noonedeadpunk | it can be all formulated as one point in cycle-highlights :) | |
| 07:17:00 | bauzas | glancing at https://review.opendev.org/c/openstack/nova-specs/+/938823/4/specs/2025.2/approved/network-id-query.rst, this was apparently a Nova API performance change, not something related to libvirt | |
| 07:17:18 | bauzas | but I can be wrong | |